LLMs · Cohere

Command R (08-2024) 32B

Name: Command R (08-2024) 32B
Author: Cohere

Parameters: 32B
Architecture: Dense
Max context: 128K tokens
License: cc-by-nc-4.0
Released: 2024-08

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run command-r:35b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/lmstudio-community/c4ai-command-r-08-2024-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/c4ai-command-r-08-2024-GGUF

Original weights · Hugging Face

Full-precision files from Cohere, for fine-tuning, vLLM, Transformers.

huggingface.co/CohereLabs/c4ai-command-r-08-2024 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run Command R (08-2024) 32B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 32.3B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	Ollama library	macOSWindowsLinux	llama.cpp, MLX	`ollama run command-r:35b`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/c4ai-command-r-08-2024-4bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve CohereLabs/c4ai-command-r-08-2024`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path CohereLabs/c4ai-command-r-08-2024`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull lmstudio-community/c4ai-command-r-08-2024-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
GPT4All	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get GPT4All
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
exo	Server	MLX	macOSLinux	MLX	Get exo
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	12.9 GB	14.9 GB	18.9 GB
`Q3_K_M`	Low	15.8 GB	17.8 GB	21.8 GB	GGUF (Q3_K_L) (opens in a new tab)
`Q4_K_M`	Good	19.7 GB	21.6 GB	25.7 GB	GGUF (opens in a new tab)
`Q5_K_M`	High	22.9 GB	24.9 GB	28.9 GB
`Q6_K`	High	26.5 GB	28.4 GB	32.5 GB	GGUF (opens in a new tab)
`Q8_0`	Very high	34.2 GB	36.2 GB	40.2 GB	GGUF (opens in a new tab)
`F16`	Full	64.6 GB	66.5 GB	70.6 GB	Original weights (opens in a new tab)

Best hardware for Command R (08-2024) 32B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q2_K.

Quality	Hardware	Quant	Memory	Speed	Runs
60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`Q5_K_M`	26.5 GB / 32.0 GB	56.3 tok/s	Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`Q4_K_M`	22.8 GB / 24.0 GB	38.3 tok/s	Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`Q4_K_M`	22.8 GB / 24.0 GB	35.6 tok/s	Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`Q4_K_M`	22.8 GB / 24.0 GB	31.4 tok/s	Runs welltight fit
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`Q6_K`	33.2 GB / 96.0 GB	47.3 tok/s	Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`Q4_K_M`	25.5 GB / 48.0 GB	17.9 tok/s	Runs well
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q2_K`	15.7 GB / 16.0 GB	41.9 tok/s	Runs welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q2_K`	15.7 GB / 16.0 GB	45.9 tok/s	Runs welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`Q2_K`	15.7 GB / 16.0 GB	55.9 tok/s	Runs welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`Q2_K`	15.7 GB / 16.0 GB	59.9 tok/s	Runs welltight fit

Check it on your own hardware

Run it on a cluster

Devices that can’t run Command R (08-2024) 32B alone can run it together. These example clusters do:

Four Raspberry Pi 5s (16 GB)0.4 tok/s at Q6_K with llama.cpp RPC

Try it with your own devices

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.